US20050235111A1 - Methods for operating a CPU having an internal data cache - Google Patents

Methods for operating a CPU having an internal data cache Download PDF

Info

Publication number
US20050235111A1
US20050235111A1 US10/523,517 US52351705A US2005235111A1 US 20050235111 A1 US20050235111 A1 US 20050235111A1 US 52351705 A US52351705 A US 52351705A US 2005235111 A1 US2005235111 A1 US 2005235111A1
Authority
US
United States
Prior art keywords
processor
data
processor chip
interface
memory
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
US10/523,517
Other versions
US7676631B2 (en
Inventor
Taro Kamiko
Pramod Pandey
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
MaxLinear Inc
Original Assignee
Individual
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Individual filed Critical Individual
Assigned to INFINEON TECHNOLOGIES AG reassignment INFINEON TECHNOLOGIES AG ASSIGNMENT OF ASSIGNORS INTEREST (SEE DOCUMENT FOR DETAILS). Assignors: KAMIKO, TARO, PANDEY, PRAMOD
Publication of US20050235111A1 publication Critical patent/US20050235111A1/en
Application granted granted Critical
Publication of US7676631B2 publication Critical patent/US7676631B2/en
Assigned to INFINEON TECHNOLOGIES WIRELESS SOLUTIONS GMBH reassignment INFINEON TECHNOLOGIES WIRELESS SOLUTIONS GMBH ASSIGNMENT OF ASSIGNORS INTEREST (SEE DOCUMENT FOR DETAILS). Assignors: INFINEON TECHNOLOGIES AG
Assigned to LANTIQ DEUTSCHLAND GMBH reassignment LANTIQ DEUTSCHLAND GMBH ASSIGNMENT OF ASSIGNORS INTEREST (SEE DOCUMENT FOR DETAILS). Assignors: INFINEON TECHNOLOGIES WIRELESS SOLUTIONS GMBH
Assigned to DEUTSCHE BANK AG NEW YORK BRANCH, AS COLLATERAL AGENT reassignment DEUTSCHE BANK AG NEW YORK BRANCH, AS COLLATERAL AGENT GRANT OF SECURITY INTEREST IN U.S. PATENTS Assignors: LANTIQ DEUTSCHLAND GMBH
Assigned to Lantiq Beteiligungs-GmbH & Co. KG reassignment Lantiq Beteiligungs-GmbH & Co. KG RELEASE OF SECURITY INTEREST RECORDED AT REEL/FRAME 025413/0340 AND 025406/0677 Assignors: DEUTSCHE BANK AG NEW YORK BRANCH, AS COLLATERAL AGENT
Assigned to Lantiq Beteiligungs-GmbH & Co. KG reassignment Lantiq Beteiligungs-GmbH & Co. KG MERGER AND CHANGE OF NAME (SEE DOCUMENT FOR DETAILS). Assignors: Lantiq Beteiligungs-GmbH & Co. KG, LANTIQ DEUTSCHLAND GMBH
Assigned to INTEL CORPORATION reassignment INTEL CORPORATION ASSIGNMENT OF ASSIGNORS INTEREST (SEE DOCUMENT FOR DETAILS). Assignors: Lantiq Beteiligungs-GmbH & Co. KG
Assigned to MAXLINEAR, INC. reassignment MAXLINEAR, INC. ASSIGNMENT OF ASSIGNORS INTEREST (SEE DOCUMENT FOR DETAILS). Assignors: INTEL CORPORATION
Assigned to WELLS FARGO BANK, NATIONAL ASSOCIATION reassignment WELLS FARGO BANK, NATIONAL ASSOCIATION SECURITY AGREEMENT Assignors: EXAR CORPORATION, MAXLINEAR COMMUNICATIONS, LLC, MAXLINEAR, INC.
Adjusted expiration legal-status Critical
Expired - Lifetime legal-status Critical Current

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F12/00Accessing, addressing or allocating within memory systems or architectures
    • G06F12/02Addressing or allocation; Relocation
    • G06F12/06Addressing a physical block of locations, e.g. base addressing, module addressing, memory dedication
    • G06F12/0638Combination of memories, e.g. ROM and RAM such as to permit replacement or supplementing of words in one module by words in another module
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F12/00Accessing, addressing or allocating within memory systems or architectures
    • G06F12/02Addressing or allocation; Relocation
    • G06F12/08Addressing or allocation; Relocation in hierarchically structured memory systems, e.g. virtual memory systems
    • G06F12/0802Addressing of a memory level in which the access to the desired data or data block requires associative addressing means, e.g. caches

Definitions

  • the present invention relates to methods for using a CPU cache memory, to chipsets which perform the method, and to devices incorporating those chipsets.
  • a CPU integrated circuit which is a CPU has access to two forms of memory: a first memory (“data cache”) within the CPU, and an external memory stored on one or more memory chips.
  • the processor of the CPU is able to access the data cache more quickly than the external memory, but the capacity of the data cache is smaller than that of the external memory, and for many calculations the CPU requires the full capacity of the external memory. For this reason, the data cache is arranged to store a duplicate of the data in the external memory. The processor can then access the data cache when it requires the duplicated data, and the external memory when it requires data which is not duplicated in the internal memory.
  • FIG. 1 shows that when the processor 1 of the CPU 3 needs to access data with a given address it does so via a cache controller 5 which determines whether the data with that address is stored in the data cache 7 . If so, the data is read from there. If not, the data is read from external memory 9 (which may take the form of one or more memory chips) using a system bus 11 . Once the CPU 3 reads data from the external memory 9 , the data will be mirrored in the data cache 7 , and the next read access from the same location in the external memory 9 will be skipped and instead the data will be taken from the data cache 7 .
  • a cache controller 5 which determines whether the data with that address is stored in the data cache 7 . If so, the data is read from there. If not, the data is read from external memory 9 (which may take the form of one or more memory chips) using a system bus 11 .
  • the system of FIG. 1 normally includes an address decoder (not shown) which is involved in passing the signals between the CPU 3 and the external memory 9 .
  • This address decoder (not shown) is employed because the external memory 9 may be partitioned, and the address decoder defines a mapping between the address in the CPU memory space and an address in the external memory 9 . For example, when the CPU 3 issues a write instruction the decoder converts the output address of the CPU 3 in the memory space of the CPU into the address of the corresponding location in the partitioned external memory 9 .
  • the memory address map of the system of FIG. 1 in the memory space of the CPU is illustrated in FIG. 2 . All of this memory corresponds to addresses in the external memory 9 (under the mapping defined by the decoder).
  • the address space includes a “memory” section 4 which the processor 1 employs as the read/write memory for performing its operations (varying portions of this memory space are mirrored in the data cache 7 ), and a “reserved” section 6 which is an area of memory which is not in fact required for performing calculations.
  • the present invention aims to provide a new and useful way of accessing a memory, and a chip set which implements the method.
  • the present invention is based on the realisation that the processes of the computer could be implemented with higher performance if only the memory stored in the data cache is used. For example, in a system in which there are several processors, performance would be improved if one or more of those processors used only their respective internal data caches. This higher performance may result from either or both of faster memory access and reduced external memory requirements.
  • the present invention proposes that a CPU having an internal data cache is operated in combination with a dummy interface which simulates the existence of an external memory having the same address space as the cache memory but which does not store data written to it.
  • a CPU according to present designs can be operated without the ability to store data in an external memory in respect of at least part of its memory address space.
  • a first expression of the present invention is a data processing system having:
  • the processor(s) can also be connected, e.g. via the dummy interface, to an external memory chip which provides data to initialise the data cache.
  • the at least one processor chip may be one or more of a plurality of processor chips which also includes at least one processor chip having access to an external memory store.
  • a second expression of the invention is a method of operating a processing chip having a processor, an internal data cache and a cache controller for transmitting write instructions out of the integrated circuit for updating an external memory, the method including discarding the write instructions and arranging for the program code operated by the processor to require only the data cache as memory.
  • FIG. 1 shows schematically a known data processing system
  • FIG. 2 shows the address map for the system of FIG. 1 ;
  • FIG. 3 shows schematically a data processing system according to the present invention
  • FIG. 4 shows an external memory simulated by the system of FIG. 3 ;
  • FIG. 5 shows the address map for the system of FIG. 3 ;
  • FIG. 6 shows a system incorporating an arrangement as shown in FIG. 3 .
  • the data processing system includes a CPU processor chip 3 having an internal processor 1 , a cache controller 5 and an internal data cache 7 connected via the system bus 11 to a dummy interface 13 .
  • the dummy interface 13 is coupled to a memory 19 , and to an address decoder 15 .
  • the dummy interface 13 reads data (including program code) which is required to initialise the CPU 3 from the memory 19 into part of the data cache 7 .
  • the processor 1 operates exactly as in present systems.
  • the program code which it runs i.e. the program code uploaded from the memory 19 during the initialisation
  • the cache controller 5 operates in the conventional manner, performing write operations to the data cache 7 and attempting to keep an (in fact non-existent) external memory 17 updated to mirror what is in the data cache 7 by transmitting write operations to the system bus 11 .
  • These write instructions are passed to the dummy interface 13 which simply discards the data it receives.
  • the address decoder 15 operates in a way similar to that of the prior art decoder discussed above, but with the difference that it never directs read/write commands from the CPU to the external memory 9 .
  • Write commands from the CPU 3 are simply discarded by the dummy interface 13 and the decoder 15 .
  • the dummy interface receives a read command from the CPU 3 (as in some embodiments it may do during the initiation procedure)
  • the dummy interface transmits an output which is not dependent on the data which has previously been transmitted to it, e.g. it may always output “0”. This feature may be used during an initialisation of the data cache 7 in which portions of the memory which are not copied from the external memory 19 may be initialised to zero using values read from the dummy interface 13 .
  • the processor 1 Since the program code is such that the only memory required is provided by the data cache 7 , the processor 1 operates in exactly the same manner as it would in the system of FIG. 1 running the same code. However, the system of FIG. 3 has the advantage that less memory is required, since the external memory 19 of FIG. 3 is only required to store the initialisation data and may be smaller than the memory 9 of FIG. 1 .
  • FIG. 5 the address map for the system is shown.
  • the memory space of the CPU 3 is entirely defined by the data cache 7 .
  • a portion 14 of the data cache stores data which was read from the external memory 19 during initialisation, and this section is not overwritten during the operation of the processor 1 .
  • a second portion 16 of the data cache 7 is the read/write area which the processor 1 uses to perform its calculations.
  • a portion 18 of data cache 7 is “reserved”, i.e. unused in the operations of the processor 1 .
  • the CPU 3 may be one of a plurality of processing units which are part of the data processing system, such as the shown in FIG. 6 having a master processing unit 20 and a plurality of slave processing units 21 .
  • one or more of the CPU processing units e.g. the master processing unit 20 only
  • Other of the CPU processing units e.g. some or all of the slave processing units 21
  • may be as discussed above in relation to FIG. 3 i.e.
  • dummy interfaces 25 initialise the slave processing unit 21 using one or more memory chips 29 which do not store data during the subsequent processing operation. In this way, the overall performance of the system is improved, since fewer read/write memories 23 are required. At the same time, the processing speed of the system is improved since many of the processors (e.g. the slave processing units 21 ) never need to wait to obtain data from external memories.
  • the only processor chip(s) 20 which are provided with the capacity to read/write data to/from an external memory 23 are the one(s) which require a read/write memory larger than their internal data cache to perform their tasks, and the program code which the full set of processing chips 20 , 21 operate is written such that all tasks which require a memory larger than the internal data cache of the cpus are allotted to those cpu(s) 20 which have access to an external memory.

Abstract

A CPU 3 having a processor 1 and an internal data cache 7 IS operated in combination with a dummy interface 13 which simulates the existence of an external memory 17 having the same address space as the cache memory 7 but which does not store data written to it. In this way, a conventional CPU can be operated without read/write access to an external memory in respect of at least part of its memory address space, and therefore with a higher performance resulting from faster memory access and reduced external memory requirements. The CPU 3 may be one of a set of CPU chips 20, 21 in a data processing system, one or more of those chips 20 optionally having read/write access to an external memory 23.

Description

    FIELD OF THE INVENTION
  • The present invention relates to methods for using a CPU cache memory, to chipsets which perform the method, and to devices incorporating those chipsets.
  • BACKGROUND OF THE INVENTION
  • Conventionally, a CPU integrated circuit which is a CPU has access to two forms of memory: a first memory (“data cache”) within the CPU, and an external memory stored on one or more memory chips. The processor of the CPU is able to access the data cache more quickly than the external memory, but the capacity of the data cache is smaller than that of the external memory, and for many calculations the CPU requires the full capacity of the external memory. For this reason, the data cache is arranged to store a duplicate of the data in the external memory. The processor can then access the data cache when it requires the duplicated data, and the external memory when it requires data which is not duplicated in the internal memory.
  • The configuration is illustrated in FIG. 1 which shows that when the processor 1 of the CPU 3 needs to access data with a given address it does so via a cache controller 5 which determines whether the data with that address is stored in the data cache 7. If so, the data is read from there. If not, the data is read from external memory 9 (which may take the form of one or more memory chips) using a system bus 11. Once the CPU 3 reads data from the external memory 9, the data will be mirrored in the data cache 7, and the next read access from the same location in the external memory 9 will be skipped and instead the data will be taken from the data cache 7. When the processor writes data into the data cache 7 it is not normally copied into the external memory 9 at once, but instead written into the external memory 9 when the corresponding data in the data cache 7 is going to be replaced. Note that the system of FIG. 1 normally includes an address decoder (not shown) which is involved in passing the signals between the CPU 3 and the external memory 9. This address decoder (not shown) is employed because the external memory 9 may be partitioned, and the address decoder defines a mapping between the address in the CPU memory space and an address in the external memory 9. For example, when the CPU 3 issues a write instruction the decoder converts the output address of the CPU 3 in the memory space of the CPU into the address of the corresponding location in the partitioned external memory 9.
  • The memory address map of the system of FIG. 1 in the memory space of the CPU is illustrated in FIG. 2. All of this memory corresponds to addresses in the external memory 9 (under the mapping defined by the decoder). The address space includes a “memory” section 4 which the processor 1 employs as the read/write memory for performing its operations (varying portions of this memory space are mirrored in the data cache 7), and a “reserved” section 6 which is an area of memory which is not in fact required for performing calculations.
  • SUMMARY OF THE INVENTION
  • The present invention aims to provide a new and useful way of accessing a memory, and a chip set which implements the method.
  • The present invention is based on the realisation that the processes of the computer could be implemented with higher performance if only the memory stored in the data cache is used. For example, in a system in which there are several processors, performance would be improved if one or more of those processors used only their respective internal data caches. This higher performance may result from either or both of faster memory access and reduced external memory requirements.
  • In general terms, the present invention proposes that a CPU having an internal data cache is operated in combination with a dummy interface which simulates the existence of an external memory having the same address space as the cache memory but which does not store data written to it. In this way, a CPU according to present designs can be operated without the ability to store data in an external memory in respect of at least part of its memory address space.
  • Specifically, a first expression of the present invention is a data processing system having:
      • at least one processor chip including a processor unit and an internal data cache, and
      • a dummy interface which receives data written to it by the processor chip, and discards it.
  • The processor(s) can also be connected, e.g. via the dummy interface, to an external memory chip which provides data to initialise the data cache.
  • The at least one processor chip may be one or more of a plurality of processor chips which also includes at least one processor chip having access to an external memory store.
  • A second expression of the invention is a method of operating a processing chip having a processor, an internal data cache and a cache controller for transmitting write instructions out of the integrated circuit for updating an external memory, the method including discarding the write instructions and arranging for the program code operated by the processor to require only the data cache as memory..
  • BRIEF DESCRIPTION OF THE FIGURES
  • An embodiment of the invention will now be described for the sake of illustration only with reference to the following figures, in which:
  • FIG. 1 shows schematically a known data processing system;
  • FIG. 2 shows the address map for the system of FIG. 1;
  • FIG. 3 shows schematically a data processing system according to the present invention;
  • FIG. 4 shows an external memory simulated by the system of FIG. 3;
  • FIG. 5 shows the address map for the system of FIG. 3; and
  • FIG. 6 shows a system incorporating an arrangement as shown in FIG. 3.
  • DETAILED DESCRIPTION OF THE EMBODIMENTS
  • The embodiment is illustrated in FIG. 3, in which components which may be identical to those shown in FIG. 1 are illustrated by the same reference numerals. As shown in FIG. 3, the data processing system includes a CPU processor chip 3 having an internal processor 1, a cache controller 5 and an internal data cache 7 connected via the system bus 11 to a dummy interface 13. The dummy interface 13 is coupled to a memory 19, and to an address decoder 15.
  • In an initialisation stage, the dummy interface 13 reads data (including program code) which is required to initialise the CPU 3 from the memory 19 into part of the data cache 7.
  • Subsequently, in operation, the processor 1 operates exactly as in present systems. However, the program code which it runs (i.e. the program code uploaded from the memory 19 during the initialisation) is such that the amount of memory required by the processor 1 is provided by the data cache 7. The cache controller 5 operates in the conventional manner, performing write operations to the data cache 7 and attempting to keep an (in fact non-existent) external memory 17 updated to mirror what is in the data cache 7 by transmitting write operations to the system bus 11. These write instructions are passed to the dummy interface 13 which simply discards the data it receives.
  • The address decoder 15 operates in a way similar to that of the prior art decoder discussed above, but with the difference that it never directs read/write commands from the CPU to the external memory 9. Write commands from the CPU 3 are simply discarded by the dummy interface 13 and the decoder 15. In the case that the dummy interface receives a read command from the CPU 3 (as in some embodiments it may do during the initiation procedure), the dummy interface transmits an output which is not dependent on the data which has previously been transmitted to it, e.g. it may always output “0”. This feature may be used during an initialisation of the data cache 7 in which portions of the memory which are not copied from the external memory 19 may be initialised to zero using values read from the dummy interface 13.
  • We now analyse the situation from the perspective of the CPU 3. The operation of the CPU is identical to what it would be if the dummy interface were not just discarding data, but instead was a normal interface performing read/write operations to a memory 17, operating as shown in FIG. 3: that is, not storing (“N/C”) any data written to it, and always outputting the value “0” in any read operation. In fact, this memory 17 does not exist, but the CPU 3 has no way of “knowing” this.
  • Since the program code is such that the only memory required is provided by the data cache 7, the processor 1 operates in exactly the same manner as it would in the system of FIG. 1 running the same code. However, the system of FIG. 3 has the advantage that less memory is required, since the external memory 19 of FIG. 3 is only required to store the initialisation data and may be smaller than the memory 9 of FIG. 1.
  • Turning to FIG. 5, the address map for the system is shown. In this case, the memory space of the CPU 3 is entirely defined by the data cache 7. A portion 14 of the data cache stores data which was read from the external memory 19 during initialisation, and this section is not overwritten during the operation of the processor 1. A second portion 16 of the data cache 7 is the read/write area which the processor 1 uses to perform its calculations. A portion 18 of data cache 7 is “reserved”, i.e. unused in the operations of the processor 1.
  • Note that the CPU 3 may be one of a plurality of processing units which are part of the data processing system, such as the shown in FIG. 6 having a master processing unit 20 and a plurality of slave processing units 21. In this case, one or more of the CPU processing units (e.g. the master processing unit 20 only) may be provided with an external memory 23 which is kept updated to mirror that processing unit's internal data cache by a conventional method such as that described above in relation to FIG. 1. Other of the CPU processing units (e.g. some or all of the slave processing units 21) may be as discussed above in relation to FIG. 3, i.e. not being able to store data an external memory but instead performing processing only using their internal data caches and transmitting their write instructions to dummy interfaces 25 which discard them. The dummy interfaces initialise the slave processing unit 21 using one or more memory chips 29 which do not store data during the subsequent processing operation. In this way, the overall performance of the system is improved, since fewer read/write memories 23 are required. At the same time, the processing speed of the system is improved since many of the processors (e.g. the slave processing units 21) never need to wait to obtain data from external memories.
  • In such a system, the only processor chip(s) 20 which are provided with the capacity to read/write data to/from an external memory 23 are the one(s) which require a read/write memory larger than their internal data cache to perform their tasks, and the program code which the full set of processing chips 20, 21 operate is written such that all tasks which require a memory larger than the internal data cache of the cpus are allotted to those cpu(s) 20 which have access to an external memory.

Claims (15)

1. A data processing system having:
at least one processor chip including a processor unit and an internal data cache, and
an interface which receives data to be written from the processor chip, the interface discarding the data received from the processor chip.
2. A data processing system according to claim 1 in which the interface is coupled to a memory, the interface passing data to the processor chip during initialization.
3. A data processing system according to claim 1 further including one or more further processing chips which have read/write access to external memory.
4. A method of operating a processing chip having a processor, an internal data cache and a cache controller for transmitting write instructions out of the integrated circuit, the method including discarding the write instructions and arranging for the program code operated by the processor to require only the data cache as memory.
5. A data processing system according to claim 1 wherein the at least one processor chip comprises exactly one processor chip.
6. A data processing system according to claim 1 wherein the at least one processor chip comprises two processor chips.
7. A data processing system according to claim 1 wherein the processor chip further includes an internal cache controller coupled between the internal data cache and the processor unit.
8. A data processing system comprising:
a processor chip including an internal processor coupled to an internal data cache;
an external memory; and
an interface coupled between the processor chip and the external memory, the interface configured to receive memory data from the external memory and transfer the memory data to the processor chip, the interface further configured to receive processor data from the processor chip and discard the processor data.
9. The system of claim 8 and further comprising a control circuit coupled to the interface circuit, the control circuit providing a control signal to indicate whether data received by the interface should be discarded.
10. The system of claim 9 wherein the control circuit comprises a decoder.
11. The system of claim 8 and further comprising:
a second processor chip that includes an internal processor coupled to an internal cache; and
a second interface, wherein the second processor chip is coupled to the external memory through the second interface.
12. The system of claim 11 and further comprising a system bus coupled to the processor chip, the second processor chip, the interface, and the second interface.
13. The system of claim 12 and further comprising a third processor chip coupled to the system bus.
14. The system of claim 13 wherein the third processor chip comprises a master processing unit and wherein the processor chip and the second processor chip comprise slave processing units.
15. The system of claim 14 and further comprising a second external memory coupled to the system bus without an interface coupled between the second external memory and the system bus.
US10/523,517 2002-08-05 2002-08-05 Methods for operating a CPU having an internal data cache Expired - Lifetime US7676631B2 (en)

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/SG2002/000176 WO2004023312A1 (en) 2002-08-05 2002-08-05 Methods for operating a cpu having an internal data cache

Publications (2)

Publication Number Publication Date
US20050235111A1 true US20050235111A1 (en) 2005-10-20
US7676631B2 US7676631B2 (en) 2010-03-09

Family

ID=31974281

Family Applications (1)

Application Number Title Priority Date Filing Date
US10/523,517 Expired - Lifetime US7676631B2 (en) 2002-08-05 2002-08-05 Methods for operating a CPU having an internal data cache

Country Status (3)

Country Link
US (1) US7676631B2 (en)
CN (1) CN1326050C (en)
WO (1) WO2004023312A1 (en)

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US8103862B2 (en) * 2008-06-25 2012-01-24 Dell Products L.P. Self test initialization
CN103294613B (en) * 2013-06-28 2016-02-24 曙光信息产业(北京)有限公司 The access method of storer

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5157780A (en) * 1990-06-12 1992-10-20 Advanced Micro Devices, Inc. Master-slave checking system
US5401199A (en) * 1992-10-21 1995-03-28 Sanshin Kogyo Kabushiki Kaisha Outboard motor engine
US5692149A (en) * 1995-03-16 1997-11-25 Samsung Electronics Co., Ltd. Block replacement method in cache only memory architecture multiprocessor
US5809531A (en) * 1992-09-21 1998-09-15 Intel Corporation Computer system for executing programs using an internal cache without accessing external RAM
US5829038A (en) * 1996-06-20 1998-10-27 Intel Corporation Backward inquiry to lower level caches prior to the eviction of a modified line from a higher level cache in a microprocessor hierarchical cache structure

Family Cites Families (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPS55500695A (en) * 1978-08-12 1980-09-25
EP0535537A3 (en) 1991-09-30 1993-04-21 Kabushiki Kaisha Toshiba Computer system with a cache memory
CA2130407A1 (en) * 1993-12-30 1995-07-01 Fu Lam Chan Store in cache having direct slave interface
US6216224B1 (en) 1998-06-05 2001-04-10 Micron Technology Inc. Method for read only memory shadowing
US6249851B1 (en) * 1998-08-25 2001-06-19 Stmicroelectronics, Inc. Computer system having non-blocking cache and pipelined bus interface unit

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5157780A (en) * 1990-06-12 1992-10-20 Advanced Micro Devices, Inc. Master-slave checking system
US5809531A (en) * 1992-09-21 1998-09-15 Intel Corporation Computer system for executing programs using an internal cache without accessing external RAM
US5401199A (en) * 1992-10-21 1995-03-28 Sanshin Kogyo Kabushiki Kaisha Outboard motor engine
US5692149A (en) * 1995-03-16 1997-11-25 Samsung Electronics Co., Ltd. Block replacement method in cache only memory architecture multiprocessor
US5829038A (en) * 1996-06-20 1998-10-27 Intel Corporation Backward inquiry to lower level caches prior to the eviction of a modified line from a higher level cache in a microprocessor hierarchical cache structure

Also Published As

Publication number Publication date
WO2004023312A1 (en) 2004-03-18
CN1326050C (en) 2007-07-11
CN1639693A (en) 2005-07-13
US7676631B2 (en) 2010-03-09

Similar Documents

Publication Publication Date Title
KR100950871B1 (en) Memory hub and access method having internal row caching
US6571319B2 (en) Methods and apparatus for combining a plurality of memory access transactions
US7644253B2 (en) Memory hub with internal cache and/or memory access prediction
AU651747B2 (en) Arbitration control logic for computer system having dual bus architecture
US5659696A (en) Method and apparatus for determining address location and taking one of two actions depending on the type of read/write data transfer required
US20020103988A1 (en) Microprocessor with integrated interfaces to system memory and multiplexed input/output bus
US6546459B2 (en) Redundant data storage systems and methods of operating a redundant data storage system
JPS6259822B2 (en)
JP3523286B2 (en) Sequential data transfer type memory and computer system using sequential data transfer type memory
US5175831A (en) System register initialization technique employing a non-volatile/read only memory
US5416916A (en) Structure for enabling direct memory-to-memory transfer with a fly-by DMA unit
US5944806A (en) Microprocessor with versatile addressing
EP0581698A1 (en) Programmable microprocessor booting technique
EP0533427A1 (en) Computer memory control system
US6684303B2 (en) Method and device to use memory access request tags
US5829035A (en) System and method for preventing stale data in multiple processor computer systems
US7676631B2 (en) Methods for operating a CPU having an internal data cache
US6119191A (en) Performing PCI access cycles through PCI bridge hub routing
EP1596280A1 (en) Pseudo register file write ports
KR100261154B1 (en) Dma controller
JPH10289197A (en) Burst transfer method for processor data and computer system
US7689864B2 (en) Processor comprising an integrated debugging interface controlled by the processing unit of the processor
JP4431492B2 (en) Data transfer unit that supports multiple coherency granules
US6356976B1 (en) LSI system capable of reading and writing at high speed
CN114372020A (en) Single chip system

Legal Events

Date Code Title Description
AS Assignment

Owner name: INFINEON TECHNOLOGIES AG, GERMANY

Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNORS:KAMIKO, TARO;PANDEY, PRAMOD;REEL/FRAME:016753/0086

Effective date: 20021003

Owner name: INFINEON TECHNOLOGIES AG,GERMANY

Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNORS:KAMIKO, TARO;PANDEY, PRAMOD;REEL/FRAME:016753/0086

Effective date: 20021003

FEPP Fee payment procedure

Free format text: PAYOR NUMBER ASSIGNED (ORIGINAL EVENT CODE: ASPN); ENTITY STATUS OF PATENT OWNER: LARGE ENTITY

STCF Information on status: patent grant

Free format text: PATENTED CASE

AS Assignment

Owner name: INFINEON TECHNOLOGIES WIRELESS SOLUTIONS GMBH,GERM

Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNOR:INFINEON TECHNOLOGIES AG;REEL/FRAME:024474/0958

Effective date: 20090703

Owner name: INFINEON TECHNOLOGIES WIRELESS SOLUTIONS GMBH, GER

Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNOR:INFINEON TECHNOLOGIES AG;REEL/FRAME:024474/0958

Effective date: 20090703

AS Assignment

Owner name: LANTIQ DEUTSCHLAND GMBH,GERMANY

Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNOR:INFINEON TECHNOLOGIES WIRELESS SOLUTIONS GMBH;REEL/FRAME:024529/0635

Effective date: 20091106

Owner name: LANTIQ DEUTSCHLAND GMBH, GERMANY

Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNOR:INFINEON TECHNOLOGIES WIRELESS SOLUTIONS GMBH;REEL/FRAME:024529/0635

Effective date: 20091106

AS Assignment

Owner name: DEUTSCHE BANK AG NEW YORK BRANCH, AS COLLATERAL AG

Free format text: GRANT OF SECURITY INTEREST IN U.S. PATENTS;ASSIGNOR:LANTIQ DEUTSCHLAND GMBH;REEL/FRAME:025406/0677

Effective date: 20101116

FPAY Fee payment

Year of fee payment: 4

AS Assignment

Owner name: LANTIQ BETEILIGUNGS-GMBH & CO. KG, GERMANY

Free format text: RELEASE OF SECURITY INTEREST RECORDED AT REEL/FRAME 025413/0340 AND 025406/0677;ASSIGNOR:DEUTSCHE BANK AG NEW YORK BRANCH, AS COLLATERAL AGENT;REEL/FRAME:035453/0712

Effective date: 20150415

MAFP Maintenance fee payment

Free format text: PAYMENT OF MAINTENANCE FEE, 8TH YEAR, LARGE ENTITY (ORIGINAL EVENT CODE: M1552)

Year of fee payment: 8

AS Assignment

Owner name: LANTIQ BETEILIGUNGS-GMBH & CO. KG, GERMANY

Free format text: MERGER AND CHANGE OF NAME;ASSIGNORS:LANTIQ DEUTSCHLAND GMBH;LANTIQ BETEILIGUNGS-GMBH & CO. KG;REEL/FRAME:045086/0015

Effective date: 20150303

AS Assignment

Owner name: INTEL CORPORATION, CALIFORNIA

Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNOR:LANTIQ BETEILIGUNGS-GMBH & CO. KG;REEL/FRAME:053259/0678

Effective date: 20200710

AS Assignment

Owner name: MAXLINEAR, INC., CALIFORNIA

Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNOR:INTEL CORPORATION;REEL/FRAME:053626/0636

Effective date: 20200731

AS Assignment

Owner name: WELLS FARGO BANK, NATIONAL ASSOCIATION, COLORADO

Free format text: SECURITY AGREEMENT;ASSIGNORS:MAXLINEAR, INC.;MAXLINEAR COMMUNICATIONS, LLC;EXAR CORPORATION;REEL/FRAME:056816/0089

Effective date: 20210708

MAFP Maintenance fee payment

Free format text: PAYMENT OF MAINTENANCE FEE, 12TH YEAR, LARGE ENTITY (ORIGINAL EVENT CODE: M1553); ENTITY STATUS OF PATENT OWNER: LARGE ENTITY

Year of fee payment: 12